{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XHH53RIESDB5JYQUVBQBK6AVBL","short_pith_number":"pith:XHH53RIE","schema_version":"1.0","canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","source":{"kind":"arxiv","id":"2206.07376","version":3},"attestation_state":"computed","paper":{"title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Li Xia, Qianchuan Zhao, Shuai Ma, Xiaoteng Ma","submitted_at":"2022-06-15T08:32:53Z","abstract_excerpt":"Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc. The most natural choice of risk measures is variance, which penalizes the upside volatility as much as the downside part. Instead, the (downside) semivariance, which captures the negative deviation of a random variable under its mean, is more suitable for risk-averse proposes. This paper aims at optimizing the mean-semivariance (MSV) criterion in reinforcement learning w.r.t. steady reward distribution. Since semivarianc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.07376","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T08:32:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18d78445c29f0c047c7ea7052ce0aa352c35f75c71327ac25fa6b5cf26aac14c","abstract_canon_sha256":"b99ca9ae776cadb33d97dc5cc5f5ce64c2cba9709a0e0d4b836ba860831fbb8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:13.670820Z","signature_b64":"KfjkX3X/alpP28thJ3bxTKtMt5fkb4g1tUqUMYaNBIeZOj0eIoYKtVHvIHmr8dwslGXreykJB/avTtdQsXGCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9cfddc50490c3d4e214a8601578150ae47b5f11d94bdac918f3aeb16321e448","last_reissued_at":"2026-07-05T05:49:13.670372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:13.670372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Li Xia, Qianchuan Zhao, Shuai Ma, Xiaoteng Ma","submitted_at":"2022-06-15T08:32:53Z","abstract_excerpt":"Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc. The most natural choice of risk measures is variance, which penalizes the upside volatility as much as the downside part. Instead, the (downside) semivariance, which captures the negative deviation of a random variable under its mean, is more suitable for risk-averse proposes. This paper aims at optimizing the mean-semivariance (MSV) criterion in reinforcement learning w.r.t. steady reward distribution. Since semivarianc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07376","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.07376/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.07376","created_at":"2026-07-05T05:49:13.670432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07376v3","created_at":"2026-07-05T05:49:13.670432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07376","created_at":"2026-07-05T05:49:13.670432+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHH53RIESDB5","created_at":"2026-07-05T05:49:13.670432+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHH53RIESDB5JYQU","created_at":"2026-07-05T05:49:13.670432+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHH53RIE","created_at":"2026-07-05T05:49:13.670432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL","json":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL.json","graph_json":"https://pith.science/api/pith-number/XHH53RIESDB5JYQUVBQBK6AVBL/graph.json","events_json":"https://pith.science/api/pith-number/XHH53RIESDB5JYQUVBQBK6AVBL/events.json","paper":"https://pith.science/paper/XHH53RIE"},"agent_actions":{"view_html":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL","download_json":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL.json","view_paper":"https://pith.science/paper/XHH53RIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07376&json=true","fetch_graph":"https://pith.science/api/pith-number/XHH53RIESDB5JYQUVBQBK6AVBL/graph.json","fetch_events":"https://pith.science/api/pith-number/XHH53RIESDB5JYQUVBQBK6AVBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/action/storage_attestation","attest_author":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/action/author_attestation","sign_citation":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/action/citation_signature","submit_replication":"https://pith.science/pith/XHH53RIESDB5JYQUVBQBK6AVBL/action/replication_record"}},"created_at":"2026-07-05T05:49:13.670432+00:00","updated_at":"2026-07-05T05:49:13.670432+00:00"}